US11182896B2ActiveUtilityA1

Automated segmentation of organ chambers using deep learning methods from medical imaging

84
Assignee: UNIV CALIFORNIAPriority: Oct 14, 2015Filed: Dec 11, 2019Granted: Nov 23, 2021
Est. expiryOct 14, 2035(~9.3 yrs left)· nominal 20-yr term from priority
G06V 20/64G06V 10/82G06V 10/454G06V 10/764G06T 7/0012G06V 2201/031G06T 2207/10081G06T 2207/10088G06T 7/38G06T 7/11G06T 7/162G06T 2207/20124G06T 7/149G06T 2207/20081G06T 2207/30048G06T 3/0006G06T 3/02
84
PatentIndex Score
4
Cited by
89
References
16
Claims

Abstract

A method of detecting whether or not a body chamber has an abnormal structure or function including: (a) providing a stack of images as input to a system comprising one or more hardware processors configured to obtain a stack of medical images comprising at least a representation of the body chamber inside the patient; to obtain a region of interest using a convolutional network trained to locate the body chamber, wherein the region of interest corresponds to the body chamber from each of the medical images; and to infer a shape of the body chamber using a stacked auto-encoder (AE) network trained to delineate the body chamber, wherein the AE network segments the body chamber; (b) operating the system to detect the body chamber in the images using deep convolutional networks trained to locate the body chamber, to infer a shape of the body chamber using a stacked auto-encoder trained to delineate the body chamber, and to incorporate the inferred shape into a deformable model for segmentation; and (c) detecting whether or not the body chamber has an abnormal structure, wherein an abnormal structure is indicated by a body chamber clinical indicia that is different from a corresponding known standard clinical indicia for the body chamber.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
       1. A method of detecting whether or not a body chamber has an abnormal structure or function comprising:
 (a) providing a stack of images comprising, at least a representation of the body chamber inside the patient, as input to a system, 
 (b) detecting the body chamber from each of the images using deep convolutional networks trained to locate the body chamber, 
 (c) inferring a shape of the body chamber using a stacked auto-encoder (AE) network trained to delineate the body chamber, wherein the AE network segments the body chamber, 
 (d) incorporating the inferred shape into a deformable model for segmentation, and 
 (e) detecting whether or not the body chamber has an abnormal structure, wherein an abnormal structure is indicated by a body chamber clinical indicia that is different from a corresponding known standard clinical indicia for the body chamber. 
 
     
     
       2. The method according to  claim 1 , wherein a structure of the deformable model of the body chamber is processed spatially and temporally to determine if function of the body chamber is abnormal. 
     
     
       3. The method according to  claim 2 , further comprising quantifying a degree of abnormality of the body chamber. 
     
     
       4. The method according to  claim 1 , further comprising performing contour alignment to reduce misalignment between multiple slices of medical images. 
     
     
       5. The method according to  claim 1 , wherein the clinical indicia is selected from the group consisting of: a volume of the body chamber, an ejection fraction, a mass of the body chamber or a chamber's wall thickness of the body chamber. 
     
     
       6. The method according to  claim 1 , wherein the body chamber is a chamber of a heart. 
     
     
       7. The method according to  claim 6 , wherein the chamber of the heart is selected from the group consisting of a left ventricle, a right ventricle, a left atrium and a right atrium. 
     
     
       8. The method according to  claim 1 , wherein the images comprise magnetic resonance imaging (MRI) images, ultrasound images, or CT scan data. 
     
     
       9. The method according to  claim 1 , wherein the system is configured to utilize a training data set to initialize filters randomly to train the deep convolutional networks. 
     
     
       10. The method according to  claim 9 , wherein the filters are convolved with the input medical images to obtain k convolved feature maps of size m 1 ×m 1 , computed as: 
       
         
           
             
               
                 
                   
                     
                       
                         
                           Z 
                           l 
                         
                         ⁡ 
                         
                           [ 
                           
                             i 
                             , 
                             j 
                           
                           ] 
                         
                       
                       = 
                       
                         
                           
                             ∑ 
                             
                               
                                 k 
                                 1 
                               
                               = 
                               1 
                             
                             a 
                           
                           ⁢ 
                           
                             
                               ∑ 
                               
                                 
                                   k 
                                   2 
                                 
                                 = 
                                 1 
                               
                               a 
                             
                             ⁢ 
                             
                               
                                 
                                   F 
                                   l 
                                 
                                 ⁡ 
                                 
                                   [ 
                                   
                                     
                                       k 
                                       1 
                                     
                                     , 
                                     
                                       k 
                                       2 
                                     
                                   
                                   ] 
                                 
                               
                               ⁢ 
                               
                                 I 
                                 ( 
                                 
                                   
                                     i 
                                     + 
                                     
                                       k 
                                       1 
                                     
                                     - 
                                     1 
                                   
                                   , 
                                   
                                     j 
                                     + 
                                     
                                       k 
                                       2 
                                     
                                     - 
                                     1 
                                   
                                 
                                 ] 
                               
                             
                           
                         
                         + 
                         
                           
                             b 
                             0 
                           
                           ⁡ 
                           
                             [ 
                             l 
                             ] 
                           
                         
                       
                     
                     , 
                   
                 
                 
                   
                     ( 
                     1 
                     ) 
                   
                 
               
             
           
         
       
       for 1≤i,j≤m 1 , l=1, . . . , k, and m 1 =m−a+1; and
 wherein p×p non-overlapping regions in the convolved feature maps are computed as: 
 
       
         
           
             
               
                 
                   
                     
                       
                         
                           P 
                           l 
                         
                         ⁡ 
                         
                           [ 
                           
                             
                               i 
                               1 
                             
                             , 
                             
                               j 
                               1 
                             
                           
                           ] 
                         
                       
                       = 
                       
                         
                           1 
                           p 
                         
                         ⁢ 
                         
                           
                             ∑ 
                             
                               i 
                               = 
                               
                                 1 
                                 + 
                                 
                                   
                                     ( 
                                     
                                       
                                         i 
                                         1 
                                       
                                       - 
                                       1 
                                     
                                     ) 
                                   
                                   ⁢ 
                                   p 
                                 
                               
                             
                             
                               i 
                               
                                 1 
                                 ⁢ 
                                 p 
                               
                             
                           
                           ⁢ 
                           
                             
                               ∑ 
                               
                                 j 
                                 = 
                                 
                                   1 
                                   + 
                                   
                                     
                                       ( 
                                       
                                         
                                           j 
                                           1 
                                         
                                         - 
                                         1 
                                       
                                       ) 
                                     
                                     ⁢ 
                                     p 
                                   
                                 
                               
                               
                                 
                                   j 
                                   1 
                                 
                                 ⁢ 
                                 p 
                               
                             
                             ⁢ 
                             
                               
                                 C 
                                 l 
                               
                               ⁡ 
                               
                                 [ 
                                 
                                   i 
                                   , 
                                   j 
                                 
                                 ] 
                               
                             
                           
                         
                       
                     
                     , 
                   
                 
                 
                   
                     ( 
                     2 
                     ) 
                   
                 
               
             
           
         
         for l≤i 1 , j 1 ≤m 2 , wherein m 2 =m 1 /p and p is chosen such that m 2  is an integer value. 
       
     
     
       11. The method according to  claim 1 , further comprising aligning the images of the body chamber by performing contour alignment to reduce misalignment between the short-axis images. 
     
     
       12. The method according to  claim 11 , wherein center coordinates of the images are estimated using the following quadratic assumptions for curvature:
     x   i   =a   1   i   2   +b   1   i+c   1 ,   (Equation 17),
 
     y   i   =a   2   i   2   +b   2   i+c   2    (Equation 18),
 
 wherein a 1 , b 1 , c 1 , a 2 , b 2 , c 2  are unknown parameters estimated based on minimizing the mean squared error as: 
 
       
         
           
             
               
                 
                   
                     
                       
                         a 
                         ^ 
                       
                       1 
                     
                     , 
                     
                       
                         b 
                         ^ 
                       
                       1 
                     
                     , 
                     
                       
                         
                           c 
                           ^ 
                         
                         1 
                       
                       = 
                       
                         arg 
                         ⁢ 
                         
                             
                         
                         ⁢ 
                         
                           
                             min 
                             
                               
                                 a 
                                 1 
                               
                               , 
                               
                                 b 
                                 1 
                               
                               , 
                               
                                 c 
                                 1 
                               
                             
                           
                           ⁢ 
                           
                             
                               ∑ 
                               
                                 i 
                                 = 
                                 1 
                               
                               n 
                             
                             ⁢ 
                             
                               
                                 ( 
                                 
                                   
                                     
                                       x 
                                       ~ 
                                     
                                     i 
                                   
                                   - 
                                   
                                     
                                       a 
                                       1 
                                     
                                     ⁢ 
                                     
                                       i 
                                       2 
                                     
                                   
                                   - 
                                   
                                     
                                       b 
                                       1 
                                     
                                     ⁢ 
                                     i 
                                   
                                   - 
                                   
                                     c 
                                     1 
                                   
                                 
                                 ) 
                               
                               2 
                             
                           
                         
                       
                     
                     , 
                   
                 
                 
                   
                       
                   
                 
               
               
                 
                   
                     
                       
                         a 
                         ^ 
                       
                       2 
                     
                     , 
                     
                       
                         b 
                         ^ 
                       
                       2 
                     
                     , 
                     
                       
                         
                           c 
                           ^ 
                         
                         2 
                       
                       = 
                       
                         arg 
                         ⁢ 
                         
                             
                         
                         ⁢ 
                         
                           
                             min 
                             
                               
                                 a 
                                 2 
                               
                               , 
                               
                                 b 
                                 2 
                               
                               , 
                               
                                 c 
                                 2 
                               
                             
                           
                           ⁢ 
                           
                             
                               ∑ 
                               
                                 i 
                                 = 
                                 1 
                               
                               n 
                             
                             ⁢ 
                             
                               
                                 
                                   ( 
                                   
                                     
                                       
                                         y 
                                         ~ 
                                       
                                       i 
                                     
                                     - 
                                     
                                       
                                         a 
                                         2 
                                       
                                       ⁢ 
                                       
                                         i 
                                         2 
                                       
                                     
                                     - 
                                     
                                       
                                         b 
                                         2 
                                       
                                       ⁢ 
                                       i 
                                     
                                     - 
                                     
                                       c 
                                       2 
                                     
                                   
                                   ) 
                                 
                                 2 
                               
                               . 
                             
                           
                         
                       
                     
                     , 
                   
                 
                 
                   
                       
                   
                 
               
             
           
         
       
       and
 wherein, after estimating the unknown parameters, the actual center coordinates are estimated from equations (17) and (18), and wherein the contours are registered, using an affine transformation with linear interpolation, according to the estimated center values to obtain an aligned stack of contours. 
 
     
     
       13. The method according to  claim 1 , further comprising identifying a segment of a body chamber from an output of a trained graph. 
     
     
       14. The method according to  claim 1 , further comprising obtaining filters using a sparse autoencoder (AE), which acts as a pre-training step. 
     
     
       15. The method according to  claim 13 , wherein the trained graph has two or more hidden layers. 
     
     
       16. The method according to  claim 1 , wherein the AE network is a deep convolutional AE network.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.